PyTorchKR Papers

“Image Classification”

총 17,598편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1812.06663

Attending Category Disentangled Global Context for Image Classification

In this paper, we propose a general framework for image classification using the attention mechanism and global context, which could incorporate with various network architectures to improve their performance. To investigate the capability of the global context, we compare four mathematical models and observe the global context encoded in the category disentangled conditional generative model could give more guidance as "know what is task irrelevant will also know what is relevant". Based on this observation, we define a novel Category Disentangled Global Context (CDGC) and devise a deep network to obtain it. By attending CDGC, the baseline networks could identify the objects of interest more accurately, thus improving the performance. We apply the framework to many different network architectures and compare with the state-of-the-art on four publicly available datasets. Extensive results validate the effectiveness and superiority of our approach. Code will be made public upon paper acceptance.

arXiv:1909.08612

Large e-retailer image dataset for visual search and product classification

Recent results of deep convolutional networks in visual recognition challenges open the path to a whole new set of disruptive user experiences such as visual search or recommendation. The list of companies offering this type of service is growing everyday but the adoption rate and the relevancy of results may vary a lot. We believe that the availability of large and diverse datasets is a necessary condition to improve the relevancy of such recommendation systems and facilitate their adoption. For that purpose, we wish to share with the community this dataset of more than 12M images of the 7M products of our online store classified into 5K categories. This original dataset is introduced in this article and several features are described. We also present some aspects of the winning solutions of our image classification challenge that was organized on the Kaggle platform around this set of images.

arXiv:1912.10804

Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification

In recent studies in hyperspectral imaging, biometrics and energy analytics, the framework of deep dictionary learning has shown promise. Deep dictionary learning outperforms other traditional deep learning tools when training data is limited; therefore hyperspectral imaging is one such example that benefits from this framework. Most of the prior studies were based on the unsupervised formulation; and in all cases, the training algorithm was greedy and hence sub-optimal. This is the first work that shows how to learn the deep dictionary learning problem in a joint fashion. Moreover, we propose a new discriminative penalty to the said framework. The third contribution of this work is showing how to incorporate stochastic regularization techniques into the deep dictionary learning framework. Experimental results on hyperspectral image classification shows that the proposed technique excels over all state-of-the-art deep and shallow (traditional) learning based methods published in recent times.

arXiv:2011.02188

Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios

This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectra differences. In our experiments we compare GA with a classic model optimisation through grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that during model optimisation it has access to examples similar to test data. We illustrate this with experiment highlighting the importance of a validation set.

논문 ID: document/9553372

Semi-Supervised Graph Prototypical Networks for Hyperspectral Image Classification

Graph convolutional network (GCN) is one of the most favorable semi-supervised approaches, which demonstrates encouraging performance for hyperspectral image classification (HSIC), especially under the condition of small sample sizes. In this paper, we propose a novel semi-supervised graph prototypical network (SSGPN) for high-precise HSIC. Different from prevenient GCN, we devise a prototypical layer comprising a distance-based cross-entropy (DCE) loss function and a novel temporal entropy-based regularizer (TER) in the frameworks of SSGPN. This effective layer can facilitate to generate more discriminative embedding features along with the representative prototypes to each class, so as to achieve accurate identification of various land-cover categories. Additionally, to promote computational efficiency, we present a graph normalization (G-Norm) to accelerate the convergence speed and boost the training procedure. Experimental results demonstrate that our proposed SSGPN can obtain promising performance compared with the state-of-the-art methods.

arXiv:2305.14462

Sorted Convolutional Network for Achieving Continuous Rotational Invariance

The topic of achieving rotational invariance in convolutional neural networks (CNNs) has gained considerable attention recently, as this invariance is crucial for many computer vision tasks such as image classification and matching. In this letter, we propose a Sorting Convolution (SC) inspired by some hand-crafted features of texture images, which achieves continuous rotational invariance without requiring additional learnable parameters or data augmentation. Further, SC can directly replace the conventional convolution operations in a classic CNN model to achieve its rotational invariance. Based on MNIST-rot dataset, we first analyze the impact of convolutional kernel sizes, different sampling and sorting strategies on SC's rotational invariance, and compare our method with previous rotation-invariant CNN models. Then, we combine SC with VGG, ResNet and DenseNet, and conduct classification experiments on popular texture and remote sensing image datasets. Our results demonstrate that SC achieves the best performance in the aforementioned tasks.

arXiv:1904.05160

Large-Scale Long-Tailed Recognition in an Open World

Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen instance. We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes. OLTR must handle imbalanced classification, few-shot learning, and open-set recognition in one integrated algorithm, whereas existing classification approaches focus only on one aspect and deliver poorly over the entire class spectrum. The key challenges are how to share visual knowledge between head and tail classes and how to reduce confusion between tail and open classes. We develop an integrated OLTR algorithm that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world. Our so-called dynamic meta-embedding combines a direct image feature and an associated memory feature, with the feature norm indicating the familiarity to known classes. On three large-scale OLTR datasets we curate from object-centric ImageNet, scene-centric Places, and face-centric MS1M data, our method consistently outperforms the state-of-the-art. Our code, datasets, and models enable future OLTR research and are publicly available at https://liuziwei7.github.io/projects/LongTail.html.

arXiv:2207.13021

CTVR-EHO TDA-IPH Topological Optimized Convolutional Visual Recurrent Network for Brain Tumor Segmentation and Classification

In today's world of health care, brain tumor detection has become common. However, the manual brain tumor classification approach is time-consuming. So Deep Convolutional Neural Network (DCNN) is used by many researchers in the medical field for making accurate diagnoses and aiding in the patient's treatment. The traditional techniques have problems such as overfitting and the inability to extract necessary features. To overcome these problems, we developed the Topological Data Analysis based Improved Persistent Homology (TDA-IPH) and Convolutional Transfer learning and Visual Recurrent learning with Elephant Herding Optimization hyper-parameter tuning (CTVR-EHO) models for brain tumor segmentation and classification. Initially, the Topological Data Analysis based Improved Persistent Homology is designed to segment the brain tumor image. Then, from the segmented image, features are extracted using TL via the AlexNet model and Bidirectional Visual Long Short-Term Memory (Bi-VLSTM). Next, elephant Herding Optimization (EHO) is used to tune the hyperparameters of both networks to get an optimal result. Finally, extracted features are concatenated and classified using the softmax activation layer. The simulation result of this proposed CTVR-EHO and TDA-IPH method is analyzed based on precision, accuracy, recall, loss, and F score metrics. When compared to other existing brain tumor segmentation and classification models, the proposed CTVR-EHO and TDA-IPH approaches show high accuracy (99.8%), high recall (99.23%), high precision (99.67%), and high F score (99.59%).

arXiv:2410.14833

A novel approach towards the classification of Bone Fracture from Musculoskeletal Radiography images using Attention Based Transfer Learning

Computer-aided diagnosis (CAD) is today considered a vital tool in the field of biological image categorization, segmentation, and other related tasks. The current breakthrough in computer vision algorithms and deep learning approaches has substantially enhanced the effectiveness and precision of apps built to recognize and locate regions of interest inside medical photographs. Among the different disciplines of medical image analysis, bone fracture detection, and classification have exhibited exceptional potential. Although numerous imaging modalities are applied in medical diagnostics, X-rays are particularly significant in this sector due to their broad availability, ease of use, and extensive information extraction capabilities. This research studies bone fracture categorization using the FracAtlas dataset, which comprises 4,083 musculoskeletal radiography pictures. Given the transformational development in transfer learning, particularly its efficacy in medical image processing, we deploy an attention-based transfer learning model to detect bone fractures in X-ray scans. Though the popular InceptionV3 and DenseNet121 deep learning models have been widely used, they still have the potential to be employed in crucial jobs. In this research, alongside transfer learning, a separate attention mechanism is also applied to boost the capabilities of transfer learning techniques. Through rigorous optimization, our model achieves a state-of-the-art accuracy of more than 90\% in fracture classification. This work contributes to the expanding corpus of research focused on the application of transfer learning to medical imaging, notably in the context of X-ray processing, and emphasizes the promise for additional exploration in this domain.

arXiv:1710.09926

Image Compression: Sparse Coding vs. Bottleneck Autoencoders

Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we explore the ability of sparse coding to improve reconstructed image quality for the same degree of compression. We observe that sparse image compression produces visually superior reconstructed images and yields higher values of pixel-wise measures of reconstruction quality (PSNR and SSIM) compared to bottleneck autoencoders. % In addition, we find that using alternative metrics that correlate better with human perception, such as feature perceptual loss and the classification accuracy, sparse image compression scores up to 18.06\% and 2.7\% higher, respectively, compared to bottleneck autoencoders. Although computationally much more intensive, we find that sparse coding is otherwise superior to bottleneck autoencoders for the same degree of compression.

arXiv:2309.06724

Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense

We aim to provide a general framework of for computational photography that recovers the real scene from imperfect images, via the Deep Nonparametric Convexified Filtering (DNCF). It is consists of a nonparametric deep network to resemble the physical equations behind the image formation, such as denoising, super-resolution, inpainting, and flash. DNCF has no parameterization dependent on training data, therefore has a strong generalization and robustness to adversarial image manipulation. During inference, we also encourage the network parameters to be nonnegative and create a bi-convex function on the input and parameters, and this adapts to second-order optimization algorithms with insufficient running time, having 10X acceleration over Deep Image Prior. With these tools, we empirically verify its capability to defend image classification deep networks against adversary attack algorithms in real-time.

arXiv:1512.06658

Deep Learning for Surface Material Classification Using Haptic And Visual Information

When a user scratches a hand-held rigid tool across an object surface, an acceleration signal can be captured, which carries relevant information about the surface. More importantly, such a haptic signal is complementary to the visual appearance of the surface, which suggests the combination of both modalities for the recognition of the surface material. In this paper, we present a novel deep learning method dealing with the surface material classification problem based on a Fully Convolutional Network (FCN), which takes as input the aforementioned acceleration signal and a corresponding image of the surface texture. Compared to previous surface material classification solutions, which rely on a careful design of hand-crafted domain-specific features, our method automatically extracts discriminative features utilizing the advanced deep learning methodologies. Experiments performed on the TUM surface material database demonstrate that our method achieves state-of-the-art classification accuracy robustly and efficiently.

arXiv:1912.06314

Identity Preserve Transform: Understand What Activity Classification Models Have Learnt

Activity classification has observed great success recently. The performance on small dataset is almost saturated and people are moving towards larger datasets. What leads to the performance gain on the model and what the model has learnt? In this paper we propose identity preserve transform (IPT) to study this problem. IPT manipulates the nuisance factors (background, viewpoint, etc.) of the data while keeping those factors related to the task (human motion) unchanged. To our surprise, we found popular models are using highly correlated information (background, object) to achieve high classification accuracy, rather than using the essential information (human motion). This can explain why an activity classification model usually fails to generalize to datasets it is not trained on. We implement IPT in two forms, i.e. image-space transform and 3D transform, using synthetic images. The tool will be made open-source to help study model and dataset design.

arXiv:2305.12072

Chest X-ray Image Classification: A Causal Perspective

The chest X-ray (CXR) is one of the most common and easy-to-get medical tests used to diagnose common diseases of the chest. Recently, many deep learning-based methods have been proposed that are capable of effectively classifying CXRs. Even though these techniques have worked quite well, it is difficult to establish whether what these algorithms actually learn is the cause-and-effect link between diseases and their causes or just how to map labels to photos.In this paper, we propose a causal approach to address the CXR classification problem, which constructs a structural causal model (SCM) and uses the backdoor adjustment to select effective visual information for CXR classification. Specially, we design different probability optimization functions to eliminate the influence of confounders on the learning of real causality. Experimental results demonstrate that our proposed method outperforms the open-source NIH ChestX-ray14 in terms of classification performance.

arXiv:2308.00491공식 코드 · Papers with Code

An L2-Normalized Spatial Attention Network For Accurate And Fast Classification Of Brain Tumors In 2D T1-Weighted CE-MRI Images

We propose an accurate and fast classification network for classification of brain tumors in MRI images that outperforms all lightweight methods investigated in terms of accuracy. We test our model on a challenging 2D T1-weighted CE-MRI dataset containing three types of brain tumors: Meningioma, Glioma and Pituitary. We introduce an l2-normalized spatial attention mechanism that acts as a regularizer against overfitting during training. We compare our results against the state-of-the-art on this dataset and show that by integrating l2-normalized spatial attention into a baseline network we achieve a performance gain of 1.79 percentage points. Even better accuracy can be attained by combining our model in an ensemble with the pretrained VGG16 at the expense of execution speed. Our code is publicly available at https://github.com/juliadietlmeier/MRI_image_classification

arXiv:2105.02358공식 코드 · Papers with Code

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at each position by computing a weighted sum of features using pair-wise affinities across all positions to capture the long-range dependency within a single sample. However, self-attention has quadratic complexity and ignores potential correlation between different samples. This paper proposes a novel attention mechanism which we call external attention, based on two external, small, learnable, shared memories, which can be implemented easily by simply using two cascaded linear layers and two normalization layers; it conveniently replaces self-attention in existing popular architectures. External attention has linear complexity and implicitly considers the correlations between all data samples. We further incorporate the multi-head mechanism into external attention to provide an all-MLP architecture, external attention MLP (EAMLP), for image classification. Extensive experiments on image classification, object detection, semantic segmentation, instance segmentation, image generation, and point cloud analysis reveal that our method provides results comparable or superior to the self-attention mechanism and some of its variants, with much lower computational and memory costs.

arXiv:2207.10825

Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation

Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger patterns or objects (e.g., stickers, sunglasses, etc.). We find that such external trigger signals are unnecessary, as highly effective backdoors can be easily inserted using rotation-based image transformation. Our method constructs the poisoned dataset by rotating a limited amount of objects and labeling them incorrectly; once trained with it, the victim's model will make undesirable predictions during run-time inference. It exhibits a significantly high attack success rate while maintaining clean performance through comprehensive empirical studies on image classification and object detection tasks. Furthermore, we evaluate standard data augmentation techniques and four different backdoor defenses against our attack and find that none of them can serve as a consistent mitigation approach. Our attack can be easily deployed in the real world since it only requires rotating the object, as we show in both image classification and object detection applications. Overall, our work highlights a new, simple, physically realizable, and highly effective vector for backdoor attacks. Our video demo is available at https://youtu.be/6JIF8wnX34M.

arXiv:2506.20449

Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generation

Text-to-image generative models have achieved remarkable breakthroughs in recent years. However, their application in medical image generation still faces significant challenges, including small dataset sizes, and scarcity of medical textual data. To address these challenges, we propose Med-Art, a framework specifically designed for medical image generation with limited data. Med-Art leverages vision-language models to generate visual descriptions of medical images which overcomes the scarcity of applicable medical textual data. Med-Art adapts a large-scale pre-trained text-to-image model, PixArt-$\alpha$, based on the Diffusion Transformer (DiT), achieving high performance under limited data. Furthermore, we propose an innovative Hybrid-Level Diffusion Fine-tuning (HLDF) method, which enables pixel-level losses, effectively addressing issues such as overly saturated colors. We achieve state-of-the-art performance on two medical image datasets, measured by FID, KID, and downstream classification performance.

arXiv:2101.06958

Covid-19 classification with deep neural network and belief functions

Computed tomography (CT) image provides useful information for radiologists to diagnose Covid-19. However, visual analysis of CT scans is time-consuming. Thus, it is necessary to develop algorithms for automatic Covid-19 detection from CT images. In this paper, we propose a belief function-based convolutional neural network with semi-supervised training to detect Covid-19 cases. Our method first extracts deep features, maps them into belief degree maps and makes the final classification decision. Our results are more reliable and explainable than those of traditional deep learning-based classification models. Experimental results show that our approach is able to achieve a good performance with an accuracy of 0.81, an F1 of 0.812 and an AUC of 0.875.

arXiv:1506.09179

Learning to Detect Blue-white Structures in Dermoscopy Images with Weak Supervision

We propose a novel approach to identify one of the most significant dermoscopic criteria in the diagnosis of Cutaneous Melanoma: the Blue-whitish structure. In this paper, we achieve this goal in a Multiple Instance Learning framework using only image-level labels of whether the feature is present or not. As the output, we predict the image classification label and as well localize the feature in the image. Experiments are conducted on a challenging dataset with results outperforming state-of-the-art. This study provides an improvement on the scope of modelling for computerized image analysis of skin lesions, in particular in that it puts forward a framework for identification of dermoscopic local features from weakly-labelled data.